I'd love to hear what you think! Please drop me a line and let me know what you like and what could be better. 🙏
NVIDIA GeForce RTX 5060 8GB Specs, Benchmarks & Pricing
The NVIDIA GeForce RTX 5060 is an entry-level graphics card released in 2025, featuring the Blackwell architecture based on the GB206 GPU. It offers 3,840 CUDA cores, 120 5th-generation tensor cores, and 8GB of GDDR7 memory running at 28 Gbps, delivering 153.42 AI TOPS for INT8 workloads (dense). The card provides strong performance for gaming and AI/ML applications at 1080p and 1440p resolutions while maintaining excellent power efficiency with a TDP of only 150W. The RTX 5060 supports DLSS 4, RTX Neural Shaders, and other advanced Blackwell features. It uses a PCI-Express 5.0 x16 interface and features 448 GB/s memory bandwidth on a 128-bit bus, matching the RTX 5060 Ti's bandwidth despite having less VRAM.
- Release Date: May 1, 2025
- MSRP: $299 USD
- GPU Architecture: blackwell
- Hardware-Accelerated GEMM Operations:FP64 FP32 TF32 BF16 FP16 FP8 FP4 INT8 INT4
- CUDA Compute Capability : 12.8
Considerations
- Lower tensor core count compared to other GPUs
- Lower memory capacity compared to other GPUs
- Below average FurMark (GL) (4K) performance
- Below average FurMark (VK) (4K) performance
Specifications for NVIDIA GeForce RTX 5060
| Specification | Performance Ranking |
|---|---|
| FP32 TFLOPs | |
| FP16 TFLOPs | |
| Tensor Core Count | |
| Memory Capacity (GB) | |
| Memory Bandwidth (GB/s) | |
| Int8 TOPs | |
| FP8 TFLOPs | Data not available |
| FP4 TFLOPs |
Gaming Benchmarks for NVIDIA GeForce RTX 5060
Rankings based on 814,966 real-world benchmark results from OpenBenchmarking.org
| Benchmark | Performance Ranking |
|---|---|
| FurMark (GL) (4K) | |
| FurMark (GL) (1440p) | |
| FurMark (GL) (1080p) | |
| FurMark (VK) (4K) | |
| FurMark (VK) (1440p) | |
| FurMark (VK) (1080p) |
Real-time NVIDIA GeForce RTX 5060 GPU Prices
We're tracking 97 of the NVIDIA GeForce RTX 5060 GPUs currently available for sale. The lowest average price is $423 (what's this?)
Buy NowCompare Price/Performance to other GPUs
We track real-time prices of other GPUs too so that you can compare the price/performance of the NVIDIA GeForce RTX 5060 GPU to other GPUs.
Compare GPU Price/PerformanceCompare NVIDIA GeForce RTX 5060 to Another GPU
Compare the NVIDIA GeForce RTX 5060 directly to another GPU to see specs, benchmarks, and prices side-by-side.
Compare GPUs Side-by-SidePrice History
NVIDIA GeForce RTX 5060 Price History
This chart tracks NVIDIA GeForce RTX 5060 prices over the past 6 months based on eBay listings. The yellow line shows the average of the three lowest-priced listings each day—a useful indicator for finding deals.
Trend: Over this period, the lowest average price has been up 39.4%. The current lowest average is $420, compared to a typical $324 over the period. The lowest average price is calculated as the average of the three lowest-priced listings each day.
gpupoet.com
Product Identifiers
Available from 6 Partners (10 products)
ASUS
- TUF Gaming GeForce RTX 5060 8GB GDDR7 OC Edition
- TUF-RTX5060-O8G-GAMING(model number)
- Dual GeForce RTX 5060 8GB GDDR7 OC Edition
- DUAL-RTX5060-O8G(model number)
- Prime GeForce RTX 5060 8GB GDDR7
- PRIME-RTX5060-8G(model number)
Gigabyte
- GeForce RTX 5060 GAMING OC 8G
- GV-N5060GAMING OC-8GD(model number)
- GeForce RTX 5060 EAGLE OC 8G
- GV-N5060EAGLE OC-8GD(model number)
- GeForce RTX 5060 OC Low Profile 8G
- GV-N5060OC-LP-8GD(model number)
Zotac
- ZOTAC Gaming GeForce RTX 5060 Twin Edge OC
- ZT-D50600H-10M(model number)
PNY
- XLR8 Gaming GeForce RTX 5060 VERTO EPIC-X RGB
- VCG50608DFXPB1(model number)
Palit
- GeForce RTX 5060 GamingPro OC
- NED5060S19T9-1043A(model number)
Gainward
- GeForce RTX 5060 Panther OC
- NED506019T9-1043A(model number)
References
- https://images.nvidia.com/aem-dam/Solutions/geforce/blackwell/nvidia-rtx-blackwell-gpu-architecture.pdf
- https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5060-family/
- https://www.nvidia.com/en-us/geforce/graphics-cards/compare/
- https://www.waredb.com/processor/nvidia-geforce-rtx-5060
- https://www.techpowerup.com/gpu-specs/geforce-rtx-5060.c4409
- https://www.nvidia.com/en-us/geforce/news/ultimate-guide-to-5060/
- https://www.nvidia.com/en-us/geforce/news/rtx-5060-out-now/
- https://www.asus.com/motherboards-components/graphics-cards/dual/dual-rtx5060-o8g/
- https://www.gigabyte.com/Graphics-Card/GV-N5060GAMING-OC-8GD
- https://www.tomshardware.com/pc-components/gpus/nvidia-geforce-rtx-5060-ti-and-5060-graphics-card-roundup-every-announced-card-from-every-aib-partner
Notes
- fp16TFLOPS of 153.5 is FP16 Tensor Core throughput (FP16 accumulate) with 2:4 structured sparsity, derived as AI TOPS ÷ 4 (614 ÷ 4), the rule used for every GeForce Blackwell file. Dense FP16 Tensor is 76.75 TFLOPS.
- int8TOPS of 153.42 represents non-sparse (dense) INT8 performance, derived from sparse INT8 of 306.83 TOPS ÷ 2 per NVIDIA Blackwell architecture whitepaper. With 2:4 structured sparsity, INT8 performance is 306.83 TOPS. Dense value used for consistent cross-vendor comparison.
- fp32TFLOPS of 19.18 is FP32 vector (CUDA core) throughput, which on GeForce Blackwell equals TF32 Tensor Core throughput without sparsity. On GeForce Ampere, Ada and Blackwell, dense TF32 runs at the FP32 vector rate. NVIDIA's RTX Blackwell whitepaper lists dense/sparse TF32 of 35.6/71.2 for the RTX 3090, 82.6/165.2 for the RTX 4090 and 104.8/209.5 for the RTX 5090, read from a search-result excerpt of the whitepaper rather than the PDF itself (https://images.nvidia.com/aem-dam/Solutions/geforce/blackwell/nvidia-rtx-blackwell-gpu-architecture.pdf).
- Power based on what NVIDIA refers to as "TGP (Total Graphics Power)".
- The RTX 5060 uses the GB206 chip with 3,840 CUDA cores across 30 streaming multiprocessors.
- Memory bandwidth calculated as 128-bit interface × 28 Gbps = 448 GB/s.
- Process node is 4nm with 21.9 billion transistors.
- The RTX 5060 and RTX 5060 Ti share the same memory bandwidth (448 GB/s) but differ in VRAM capacity (8GB vs 16GB).
- MSRP of $299 USD sourced from nvidia.com official product page (https://www.nvidia.com/en-us/geforce/news/rtx-5060-out-now/). No Founders Edition available; pricing is for partner cards.
- No NVIDIA Founders Edition was released for the RTX 5060. All cards are from AIB partners including ASUS, MSI, Gigabyte, Zotac, PNY, Palit, Gainward, Colorful, INNO3D, GALAX/KFA2.
- Gigabyte offers a unique low-profile RTX 5060 OC Low Profile 8G (GV-N5060OC-LP-8GD) for small form factor and server builds. It is 182mm long with three small fans.
- Third-party product identifiers sourced from official manufacturer websites (ASUS, Gigabyte), Tom's Hardware RTX 5060 roundup, Newegg, and Best Buy product listings.
- fp4TFLOPS of 307 represents non-sparse (dense) FP4 performance, derived from the official NVIDIA AI TOPS figure of 614 (FP4 sparse, per nvidia.com/en-us/geforce/graphics-cards/compare/) ÷ 2. Dense value used for consistent cross-vendor comparison.
- NOT FOUND: fp8TFLOPS — NVIDIA does not publish a standalone dense or sparse FP8 TFLOPS figure for consumer GeForce Blackwell cards; searched the NVIDIA RTX Blackwell architecture whitepaper and the official RTX 5060/compare pages (URLs in references), which list only AI TOPS (FP4 sparse), Peak TF32 Tensor TFLOPS, Peak FP16 Tensor TFLOPS, and INT8 TOPS. Left null rather than guessed from the INT8 dense value.
- supportedHardwareOperations: INT4 removed per the locked GEMM-only definition (2026-09) — neither the consumer nor datacenter Blackwell documentation lists INT4 Tensor Core support (dropped starting with Blackwell per gpu-researcher.md's canonical Blackwell table); the array now matches the canonical consumer Blackwell baseline of FP4, FP8, FP16, BF16, TF32, INT8.